How is the structure of features in the dataset?

POSTECH-CVLab / point-transformer

This is an unofficial implementation of the Point Transformer paper.

508 stars 99 forks source link

How is the structure of features in the dataset? #45

Closed John155 closed 2 years ago

John155 commented 2 years ago

I don't understand the structure of the dataset, how a point in the dataset is described. A point is described with 9 features. What are these features, and how can the network train with its own data set?

chrockey commented 2 years ago

Hi @John155,

Sorry for the late reply. Actually, each point in the dataset is described with 7 features: XYZ coordinates (3) + RGB values (3) + Semantic label (1) as described in the line below: https://github.com/POSTECH-CVLab/point-transformer/blob/8d2a38998f1ed8cd6d03fe1b671440724aa269c8/util/s3dis.py#L32

Hope this helps your understanding :).